DRP-AI TVM Makes It Easy to Port AI Model into RZ/V Devices

时间： 2023-02-09 来源：Renesas Blogs

Have you ever found it difficult to implement an AI model in an embedded device? We would like to introduce DRP-AI TVM[1] for easy porting of AI models.

In recent years, the implementation of AI in embedded devices such as surveillance cameras, traffic monitoring systems, robots, and drones has been increasing. Unlike the cloud environment, embedded devices have many considerations such as HW performance and restrictions in cost and power consumption, making AI implementation difficult. By using the AI-MPU RZ/V series, which implements RENESAS' low-power AI accelerator DRP-AI, most of the hardware implementation issues can be resolved.

When users implement AI models into MPUs, they can use the DRP-AI translator to convert AI models into DRP-AI executable format. However, we received feedback from some users about the difficulty of implementation.

The main reasons are two：

AI model format supported by the DRP-AI translator is ONNX only.
If non-supported AI model operators are included in AI models, the DRP-AI translator cannot convert it into an executable format.

Renesas has asked users to handle such cases themselves, which has caused a burden on some users. We released DRP-AI TVM to solve the issues and to improve user experience.

DRP-AI TVM is the tool that added DRP-AI support on an open-source ML compiler Apache TVM. Using DRP-AI TVM, AI model operators non-supported by DRP-AI translator can be automatically allocated to CPUs to implement more AI models into RZ/V products easily. DRP-AI TVM supports not only ONNX, and other AI frameworks such as Poarch and TensorFlow, etc.

Furthermore, as with the conventional DRP-AI translator flow, DRP-AI can handle the pre-processing of AI inference, enabling total AI performance improvement, including pre-processing.

DRP-AI TVM structure

Auto AI model operators’ allocation by DRP-AI TVM

DRP-AI TVM is public on GitHub for users to ease to access. Users can find sufficient information to use DRP-AI TVM on GitHub, such as the tutorial, sample code, and a variety of AI model performances. The tutorial includes steps from building the environment to AI inference on an evaluation board, and customers can use these steps to evaluate their AI models easily. Renesas will continue to strive for UX improvements to make it easier for customers to use Renesas products.

发送到邮箱 |
+1 赞 0
收藏
评论 0
| 转发至：

本文由酉水浪子转载自Renesas Blogs，原文标题为:DRP-AI TVM Makes It Easy to Port AI Model into RZ/V Devices，本站所有转载文章系出于传递更多信息之目的，且明确注明来源，不希望被转载的媒体或个人可与我们联系，我们将立即进行删除处理。

全部评论（0）

暂无评论

【经验】RZ/T2M使用瑞萨工具生成IAR开发环境软件项目驱动的方法

瑞萨RZ家族发布了最新的MPU型号RZ/T2系列，那么对于该系列MPU如何使用瑞萨软件工具生成IAR开发环境代码呢，如下步骤主要介绍使用瑞萨RZT Smart Configurator工具生成RZ/T2M IAR开发环境软件项目驱动方法。

2023-03-25 - 设计经验

【经验】解析瑞萨MPU RZ/T1 SPI总线通信功能配置方法

当我们使用瑞萨（Renesas）MPU RZ/T1做项目开发时，基本都会用到SPI总线通信的功能，SPI总线通信速率较快很适合在单片机板级之间进行数据交互，本文将介绍使用瑞萨开发环境配置生成RZ/T1 SPI总线驱动程序的方法。

2022-05-02 - 设计经验

【经验】瑞萨MPU RZ/T1使用SSC生成EtherCAT CiA402协议栈方法

瑞萨MPU RZ/T1支持EtherCAT网络设计，如何使用协议栈工具生成相对应的EtherCAT从机栈代码呢，本文主要就Beckhoff工具生成EtherCAT CiA402协议栈方法做相关介绍。

2021-12-26 - 设计经验

“嵌入式AI MPU ” RZ/V介绍

型号- RZ/V2L,RZ/V2M,RZ/V2XX,RZ/V2MA,RZ/V SERIES,RZ/V2XXX,RZ/V3X

2023/9/18 - RENESAS - 商品及供应商介绍查看更多版本

【经验】瑞萨RZ/T2M系列MPU使用IAR开发环境时的调试方法和注意事项

瑞萨RZ/T2M系列MPU可以使用IAR开发环境进行开发，当我们使用IAR开发环境加载一些瑞萨RZ/T2M相关例程项目时，总是会遇到一些编译报错问题，烧写异常问题，此文主要介绍使用IAR开发环境连接调试RZ/T2M系列MPU的方法和一些注意事项。

2023-03-31 - 设计经验

RZ/G MPU G2L、LC、UL组

型号- RZ/G3YYY,RZ/G2L,RZ/G2M,RZ/G2LC,RZ/G2UL,RZ/G1M,RZ/G2N,RZ/G1N,RZ/G,RZ/G1C,RZ/G2E,RZ/G1E,RZ/G2H,RZ/G1H,RZ/G3YY,RZ/G3XX,RZ/G3ZZ,RZ/G4X,RZ/G3X,RZ/G3Y,RZ/G4XX,RZ/G3Z

SEPTEMBER 2023 - RENESAS - 商品及供应商介绍

【经验】瑞萨MPU RZ/T1使用code generator生成SCI的初始代码方法

工程师初次使用瑞萨（Renesas）RZ/T1系列MPU时，可能不知道SCI该如何配置波特率，中断入口，中断标志位等。本文将介绍RZ/T1系列MPU利用code generator生产SCI的配置方法。

2022-04-22 - 设计经验

【经验】瑞萨MPU RZ/T1使用中断方式DMA传输的方法介绍

瑞萨（Renesas）MPU RZ/T1系列可以用于工业通信，伺服等领域项目中，这些领域往往需要主控与外设进行大量数据的交互，当我们使用RZ/T1的DMA中断传输功能接收大量数据时，在程序及配置中具体我们该怎么操作呢，本文主要介绍中断方式操作DMA传输的方法。

2022-06-26 - 设计经验

RZ/G MPU G2H，M，N，N组

型号- RZ/G3YYY,RZ/G2L,RZ/G2M,RZ/G2LC,RZ/G2UL,RZ/G1M,RZ/G2N,RZ/G1N,RZ/G1C,RZ/G2E,RZ/G1E,RZ/G2H,RZ/G1H,RZ/G3XX,RZ/G3YY,RZ/G3ZZ,RZ/G4X,RZ/G3X,RZ/G3Y,RZ/G4XX,RZ/G3Z

SEPTEMBER 2023 - RENESAS - 商品及供应商介绍

【经验】解析瑞萨MPU RZ/T1在e2 studio环境下的双核仿真步骤方法

瑞萨（Renesas）RZ/T1为基于32位和64位Arm的高端MPU，广泛应用工业控制领域，本文主要介绍使用瑞萨RZ/T1的双核CR4和CM3在e2 studio下的双核仿真步骤方法，帮助大家快速的进阶RZ/T1项目开发。

2022-04-12 - 设计经验

Renesas（瑞萨电子）RZ系列64位/32位基于Arm的微处理器(MPU)选型指南

目录- RZ Series MPU RZ/A Series MPU RZ/G Series MPU RZ/T Series MPU RZ/N Series MPU RZ Family MPU Package overview

型号- RZ/A1M,RZ/A1L,RZ/N1D,RZ/G1M,RZ/G1N,RZ/A1H,R8A774BX,RZ/A1LU,RZ/G1C,RZ/G1E,RZ/G1H,RZ/A1,RZ/A,RZ/G2,RZ/N,RZ/A2M,RZ/G2M,RZ/G2N,RZ/G2M 96,R8A774EX,RZ/G,RZ/N1,RZ/G2E 96,RZ/A1LC,RZ/T1,RZ/G2E,RZ/T,RZ/G2H,R8A774C0,RZ/N1S,RZ FAMILY,R8A774AX,RZ/G2M-96CE,RZ/N1L

2020.02 - RENESAS - 选型指南